© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 9457
    Prev
    Next
    INDEX
    Explanations

    final declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IDEA
    0.95
    -
    0.89
     NCBI
    0.84
     HUB
    0.82
     Audience
    0.81
     SUPPL
    0.81
     Mugh
    0.80
     Mosul
    0.79
    ఞ
    0.79
     Excellence
    0.79
    POSITIVE LOGITS
    are
    0.98
    ts
    0.98
    res
    0.93
    с
    0.90
    ato
    0.89
    asi
    0.88
    س
    0.84
    the
    0.83
    new
    0.80
    in
    0.79
    Activations Density 0.001%

    No Known Activations